Confidential · UX · AI Systems
Digital Infuzion writes proposals to win government contracts, which means tight guidelines, strict evaluation criteria, and a lot of language reused from past submissions. Over Summer 2025, I designed a prompting interface built to help their team search, adapt, and reuse past proposal content instead of rebuilding every document from scratch.
Presenting the project alongside the other interns at the end of the summer.
The most important part was making sure a person still shaped the tone, strategy, and what the client actually wanted, instead of just checking boxes; the first version of the interface prompted finished proposals, not winning ones. They were technically complete, but flat, and there wasn't much room left for the writer's own judgment.
I went back and rebuilt the flow around guided, Mad Libs style prompting, so the person writing the proposal stayed the strategist and the AI stayed a drafting assist. The rebuilt version earned staff trust across 3 major proposal cycles, including a presentation to a panel of 5 executives. I also ran a short side study on whether AI image generation could help with the graphic side of a proposal.
This project is proprietary and confidential to Digital Infuzion, so I can't post the full case study publicly; the deck below walks through the process, both versions of the interface, and what I concluded.
